AI說書 - 從0開始 - 24

我想要一天分享一點「LLM從底層堆疊的技術」，並且每篇文章長度控制在三分鐘以內，讓大家不會壓力太大，但是又能夠每天成長一點。

延續AI說書 - 從0開始 - 23示範了ChatGPT回答的能力，現在我們來看看ChatGPT撰寫程式的能力。

嘗試問以下問題：Write a detailed explanation for a beginner in Python for this code.

其回答如下：

1. Import libaries

We import several libraries that we will use throughout the code. NumPy and Pandas are used for data manipulation, Matplotlib is used for data visualization, Scikit-learn is used for machine learning, and we import specific functions like load_iris, train_test_split, DecisionTreeClassifier, confusion_matrix, and plot_tree from the respective Scikit-learn modules.

import numpy as np 
import pandas as pd 
import matplotlib.pyplot as plt 
from sklearn.datasets import load_iris 
from sklearn.model_selection import train_test_split 
from sklearn.tree import DecisionTreeClassifier 
from sklearn.metrics import confusion_matrix 
from sklearn.tree import plot_tree

2. Load the Iris dataset

We use the load_iris function from Scikit-learn's datasets module to load the Iris dataset into a variable called iris.

iris = load_iris()

3. Split the dataset into training and testing sets

We use Scikit-learn's train_test_split function to split the dataset into training and testing sets. We pass in iris.data as the features and iris.target as the labels. We set the test size to 20%, which means that 20% of the data will be used for testing and 80% will be used for training. We also set the random state to 42 to ensure that the results are reproducible.

X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.2, random_state=42)

此時，當我看著 ChatGPT 寫下到目前為止的所有內容並仍在瘋狂地打字時，我開始想我在這一切中扮演了什麼角色？人工智慧會接管我的工作嗎？儘管我知道生成式人工智慧有很多局限性，但它仍然讓我感到困惑。